The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through issue descriptions and comments.
Ingestion points: SKILL.md uses gh issue view to fetch untrusted content from issue bodies and comments.
Boundary markers: No delimiters or safety instructions are used to distinguish between system instructions and external data.
Capability inventory: The skill uses gh issue comment in SKILL.md to post content back to GitHub.
Sanitization: There is no evidence of sanitization or filtering of the retrieved content before it is processed by the model.
[COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) to interact with remote repositories.
It performs read operations using gh issue view and write operations using gh issue comment.

issue-reply